{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:38:29Z","timestamp":1757608709505,"version":"3.44.0"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128738","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"11191-11197","source":"Crossref","is-referenced-by-count":0,"title":["Continuous Control of Diverse Skills in Quadruped Robots Without Complete Expert Datasets"],"prefix":"10.1109","author":[{"given":"Jiaxin","family":"Tu","sequence":"first","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University,Shanghai,China,200433"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyi","family":"Wei","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University,Shanghai,China,200433"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University,Shanghai,China,200433"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taixian","family":"Hou","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University,Shanghai,China,200433"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Jingcheng Zhitong Robotics Technology Co.,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyan","family":"Dong","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University,Shanghai,China,200433"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhai","sequence":"additional","affiliation":[{"name":"Academy for Engineering and Technology, Fudan University,Shanghai,China,200433"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of AI and Robotics,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"volume-title":"Humanoid parkour learning","year":"2024","author":"Zhuang","key":"ref2"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/ITSC58415.2024.10920216","volume-title":"F1tenth autonomous racing with offline reinforcement learning methods","author":"Koirala","year":"2024"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1007\/978-981-99-9119-8_22","article-title":"Re- inforcement learning-based algorithm for real-time automated parking decision making","volume-title":"Artificial Intelligence","author":"Wei","year":"2024"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v35i1.16083","volume-title":"Universal trading for order execution with oracle policy distillation","author":"Fang","year":"2021"},{"volume-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","year":"2022","author":"Rudin","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560769"},{"key":"ref8","article-title":"Generative adversarial imitation learning","volume":"29","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"342","article-title":"Learning agile skills via adversarial imitation of rough partial demonstrations","volume-title":"Conference on Robot Learning.","author":"Li","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160421"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/IROS47612.2022.9981973","volume-title":"Adversarial motion priors make good substitutes for complex reward functions","author":"Escontrela","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160562"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2011.04.012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-54738-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15175"},{"key":"ref16","article-title":"Generative adversarial self- imitation learning","author":"Guo","year":"2018","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","volume-title":"Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining, ser. AAAIWS\u201994.","author":"Berndt","year":"1994"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3290509"},{"volume-title":"Advanced skills through multiple adversarial motion priors in reinforcement learning","year":"2022","author":"Vollenweider","key":"ref20"},{"volume-title":"Self-imitation learning","year":"2018","author":"Oh","key":"ref21"},{"key":"ref22","first-page":"47554","article-title":"A robust and opponent-aware league training method for starcraft ii","volume-title":"Advances in Neural Information Processing Systems","author":"Huang","year":"2023"},{"volume-title":"Reinforced self- training (rest) for language modeling","year":"2023","author":"Gulcehre","key":"ref23"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"111334","DOI":"10.1016\/j.knosys.2023.111334","article-title":"Adaptive trajectory-constrained exploration strategy for deep reinforcement learning","volume":"285","author":"Wang","year":"2024","journal-title":"Knowledge-Based Systems"},{"volume-title":"Learning self-imitating diverse policies","year":"2019","author":"Gangwani","key":"ref25"},{"volume-title":"Harnessing network effect for fake news mitigation: Selecting debunkers via self-imitation learning","year":"2024","author":"Xu","key":"ref26"},{"volume-title":"Douzero: Mastering doudizhu with self-play deep reinforcement learning","year":"2021","author":"Zha","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2024.3375515"},{"volume-title":"Independent generative adversarial self-imitation learning in cooperative multiagent systems","year":"2019","author":"Hao","key":"ref29"},{"volume-title":"Generative adversarial self-imitation learning","year":"2018","author":"Guo","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130191"},{"key":"ref32","article-title":"Proximal policy optimization algorithms","volume":"abs\/1707.06347","author":"Schulman","year":"2017","journal-title":"CoRR"},{"volume-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","year":"2021","author":"Makoviychuk","key":"ref33"},{"volume-title":"Gpu-accelerated robotic simulation for distributed reinforcement learning","year":"2018","author":"Liang","key":"ref34"},{"volume-title":"rsl_rl","year":"2024","author":"Robotic Systems Lab","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2020.2976639"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128738.pdf?arnumber=11128738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:46:58Z","timestamp":1756882018000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128738\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128738","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}